I have it on pretty good authority that Google uses secure search for indexing. I've seen some definitive test results that categorically prove that Google uses your browsing activity for finding and indexing pages, plus unofficial confirmation from former Google employees.

It's a dirty little secret.

This would be a great test for Rand Fishkin to build a case study on.

Backlinks from DA 21 sites are nothing to sneeze at. I'll take them all day long. Moz actually just rolled out a great tool called "Spam Score". The lower a spam score the better. It will show you the spam score for any links that Moz has found. Spammy links can affect your rankings, so spammy links should be investigated and possibly disavowed. If your site's own spam score is low, I wouldn't get my panties in a knot.

Where this is  appearing the most is on cross domain canonicals. We have duplicate content across 2 websites, and we've canonicaled some pages from Site A to Site B, and some from Site B to Site A. In theory, pages that were canonicaled to the other domain should be deindexed. When I run a rankings report, I see pages for the wrong domain ranking, a month later. They are pages with parameters, or old URLs that we've changed. It's like a game of whack a mole. Every time we get a page deindexed, a duplicate with a different parameter takes its place. And this is in spite of calling out these parameters in GWT.

What I imagine is happening is that we have several URLs for the same page indexed. When Google crawls our site, it is correctly canonicaling the page it crawls. In the rankings, however, Google is probably pulling a duplicate page out of its index, and ranking it without crawling it. If it was crawling it, Google would see the canonical tag, and not rank it. So we have an ongoing battle to get Google to crawl the page it just pulled out of its index to see the the canonical tag.

The reason for all this is that when a page cross domain canonicals correctly, the rankings for the duplicate page on the other site goes up dramatically. As long as Google keeps ranking the wrong pages, we don't get the rankings bump on the other site.

Due to URL changes and parameters on our ecommerce sites, we have a massive amount of duplicate pages indexed by google, sometimes up to 5 duplicate pages with different URLs.

1. We've instituted canonical tags site wide.

2. We are using the parameters function in Webmaster Tools.

3. We are using 301 redirects on all of the obsolete URLs

4. I have had many of the pages fetched so that Google can see and index the 301s and canonicals.

5. I created HTML sitemaps with the duplicate URLs, and had Google fetch and index the sitemap so that the dupes would get crawled and deindexed.

None of these seems to be terribly effective. Google is indexing pages with parameters in spite of the parameter (clicksource) being called out in GWT. Pages with obsolete URLs are indexed in spite of them having 301 redirects. Google also appears to be ignoring many of our canonical tags as well, despite the pages being identical.

Any ideas on how to clean up the mess?

IMHO, Google has essentially tied our sites together, looking at the rankings and other metrics. We've upgraded some product pages with the same result - the upgraded page and the old page on the other side are stuck on page 2. They even mirror each other in the SERPs. They both move up and down by similar numbers. If Page A drops 2 slots, page B drops 2 slots. It's like the pages are attached at the hip...

We are a large catalog company with thousands of products across 2 different domains. Google clearly knows that the sites are connected. Both domains are fairly well known brands - thousands of branded searches for each site per month. Roughly half of our products overlap - they appear on both sites. We have a known duplicate content issue - both sites having exactly the same product descriptions, and we are working on it.

We've seen that when a product has different content on the 2 sites, frequently, both pages get to page 2 of the SERPs, but that's as far as it goes, despite aggressive white hat link building tactics.

1. Is it possible to get the same product pages on page 1 of the SERPs for both sites? (I think I know the answer...)

2. Should we be canonicalizing (is that a word?) products across the sites? This would get tricky - both sites have roughly the same domain authority, but in different niches. Certain products and keywords naturally rank better on 1 site or the other depending on the niche.